Predictive assignments that relate to genetic information and leverage machine learning models

1. A system comprising: a genetic prediction server comprising: an interface that acquires records that each indicate one or more characteristics determined to exist for an individual; and a controller that selects one or more machine learning models that utilize characteristics as input, and for each individual in the records: predictively assigns at least one genetic variant to that individual by operating the one or more machine learning models, utilizing at least one characteristic indicated in the records for that individual as input to the one or more machine learning models; the controller analyzes input indicating accuracy of a predictively assigned genetic variant, and determines a score for a machine learning model based on the analyzed input and a cost function; each of the one or more machine learning models comprises a multi-layer neural network, each layer comprising multiple nodes, wherein nodes in different layers are coupled via weighted connections, nodes in an input layer of a neural network correspond with characteristics, and nodes in an output layer of a neural network correspond with genetic variants; and the controller revises the weighted connections based on the score.

2. The system of claim 1 wherein: for each individual, the one or more machine learning models predictively assign genetic variants to the individual that are distinct from a phenotype that is defined by characteristics that are already indicated in the records for that individual.

3. The system of claim 1 wherein: characteristics are each assigned a location with respect to other characteristics, and the neural networks include a layer that generates an output based on locations of characteristics with respect to each other.

4. The system of claim 3 wherein: the locations of characteristics are assigned within a category selected from the group consisting of: metabolism, socialization, fitness, perception, and pertinence to a specific aspect of health.

5. The system of claim 3 wherein: for each neural network, the controller assigns a location to each characteristic used as an input to the neural network.

6. The system of claim 1 wherein: the controller determines a confidence value for each genetic variant based on output from the one or more machine learning models, compares the confidence value to a confidence threshold for that genetic variant, and predictively assigns a genetic variant to an individual if the confidence value for that genetic variant exceeds the confidence threshold for that genetic variant.

7. The system of claim 1 wherein: each machine learning model corresponds with a different genetic variant; and each machine learning model utilizes a different combination of characteristics as input.

8. A method comprising: acquiring records that each indicate one or more characteristics determined to exist for an individual; selecting one or more machine learning models that utilize characteristics as input; for each individual in the records, predictively assigning at least one genetic variant to that individual by operating the one or more machine learning models, utilizing at least one characteristic indicated in the records for that individual as input to the one or more machine learning models; analyzing input indicating accuracy of a predictively assigned genetic variant; determining a score for a machine learning model based on the analyzed input and a cost function, wherein each of the one or more machine learning models comprises a multi-layer neural network, each layer comprising multiple nodes, wherein nodes in different layers are coupled via weighted connections, nodes in an input layer of a neural network correspond with characteristics, and nodes in an output layer of a neural network correspond with genetic variants; and revising the weighted connections based on the score.

9. The method of claim 8 wherein: for each individual, the one or more machine learning models predictively assign genetic variants to the individual that are distinct from a phenotype that is defined by characteristics that are already indicated in the records for that individual.

10. The method of claim 8 wherein: characteristics are each assigned a location with respect to other characteristics, and the neural networks include a layer that generates an output based on locations of characteristics with respect to each other.

11. The method of claim 10 wherein: the locations of characteristics are assigned within a category selected from the group consisting of: metabolism, socialization, fitness, perception, and pertinence to a specific aspect of health.

12. The method of claim 10 further comprising: for each neural network, assigning a location to each characteristic used as an input to the neural network.

13. The method of claim 8 further comprising: determining a confidence value for each genetic variant based on output from the one or more machine learning models; comparing the confidence value to a confidence threshold for that genetic variant; and predictively assigning a characteristic to an individual if the confidence value for that genetic variant exceeds the confidence threshold for that genetic variant.

14. The method of claim 8 wherein: each machine learning model corresponds with a different genetic variant; and each machine learning model utilizes a different combination of characteristics as input.

15. A non-transitory computer readable medium embodying programmed instructions which, when executed by a processor, are operable for performing a method comprising: acquiring records that each indicate one or more characteristics determined to exist for an individual; selecting one or more machine learning models that utilize characteristics as input; for each individual in the records, predictively assigning at least one genetic variant to that individual by operating the one or more machine learning models, utilizing at least one characteristic indicated in the records for that individual as input to the one or more machine learning models; analyzing input indicating accuracy of a predictively assigned genetic variant; determining a score for a machine learning model based on the analyzed input and a cost function, wherein each of the one or more machine learning models comprises a multi-layer neural network, each layer comprising multiple nodes, wherein nodes in different layers are coupled via weighted connections, nodes in an input layer of a neural network correspond with characteristics, and nodes in an output layer of a neural network correspond with genetic variants; and revising the weighted connections based on the score.

16. The medium of claim 15 wherein: for each individual, the one or more machine learning models predictively assign genetic variants to the individual that are distinct from a phenotype that is defined by characteristics that are already indicated in the records for that individual.

17. The medium of claim 15 wherein the method further comprises: wherein characteristics are each assigned a location with respect to other characteristics, and the neural networks include a layer that generates an output based on locations of characteristics with respect to each other.

18. The medium of claim 17 wherein: the locations of characteristics are assigned within a category selected from the group consisting of: metabolism, socialization, fitness, perception, and pertinence to a specific aspect of health.

19. The medium of claim 17 wherein the method further comprises: for each neural network, assigning a location to each characteristic used as an input to the neural network.

20. The medium of claim 15 wherein the method further comprises: determining a confidence value for each genetic variant based on output from the one or more machine learning models; comparing the confidence value to a confidence threshold for that genetic variant; and predictively assigning a genetic variant to an individual if the confidence value for that genetic variant exceeds the confidence threshold for that genetic variant.